[AMDGPU] eliminate frame index v_add wave32 test #107832

PankajDwivedi-25 · 2024-09-09T09:52:33Z

PR: #102346 v_add_u32_e64 test cases for wave32

llvmbot · 2024-09-09T09:52:55Z

@llvm/pr-subscribers-backend-amdgpu

Author: Pankaj Dwivedi (PankajDwivedi-25)

Changes

PR: #102346 v_add_u32_e64 test cases for wave32

Patch is 32.42 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/107832.diff

1 Files Affected:

(added) llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-co-u32-wave32.mir (+412)

diff --git a/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-co-u32-wave32.mir b/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-co-u32-wave32.mir
new file mode 100644
index 00000000000000..bb89853ea5bf34
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-co-u32-wave32.mir
@@ -0,0 +1,412 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# Test wave32
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx940 -mattr=+wavefrontsize32 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefixes=FLATSCRW32,GFX940 %s
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -mattr=+wavefrontsize32 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefixes=FLATSCRW32,GFX11 %s
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1200 -mattr=+wavefrontsize32 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefixes=FLATSCRW32,GFX12 %s
+
+
+---
+name: v_add_co_u32_e64__inline_imm__fi_offset0
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 4, alignment: 16 }
+machineFunctionInfo:
+  scratchRSrcReg:  '$sgpr0_sgpr1_sgpr2_sgpr3'
+  frameOffsetReg:  '$sgpr33'
+  stackPtrOffsetReg: '$sgpr32'
+body:             |
+  bb.0:
+    ; FLATSCRW32-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset0
+    ; FLATSCRW32: renamable $vgpr0, $vcc_lo = V_ADD_CO_U32_e64 12, $sgpr32, 0, implicit $exec
+    ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0, implicit $sgpr0
+    renamable $vgpr0, $vcc_lo = V_ADD_CO_U32_e64 12, %stack.0, 0, implicit $exec
+    SI_RETURN implicit $vgpr0, implicit $sgpr0
+
+...
+
+---
+name: v_add_co_u32_e64__inline_imm__fi_offset0__clamp
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 4, alignment: 16 }
+machineFunctionInfo:
+  scratchRSrcReg:  '$sgpr0_sgpr1_sgpr2_sgpr3'
+  frameOffsetReg:  '$sgpr33'
+  stackPtrOffsetReg: '$sgpr32'
+body:             |
+  bb.0:
+    ; FLATSCRW32-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset0__clamp
+    ; FLATSCRW32: renamable $vgpr0, dead $vcc_lo = V_ADD_CO_U32_e64 12, $sgpr32, 1, implicit $exec
+    ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+    renamable $vgpr0, dead $vcc_lo = V_ADD_CO_U32_e64 12, %stack.0, 1, implicit $exec
+    SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e64__inline_imm__fi_offset0__live_vcc_clamp
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 4, alignment: 16 }
+machineFunctionInfo:
+  scratchRSrcReg:  '$sgpr0_sgpr1_sgpr2_sgpr3'
+  frameOffsetReg:  '$sgpr33'
+  stackPtrOffsetReg: '$sgpr32'
+body:             |
+  bb.0:
+    ; FLATSCRW32-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset0__live_vcc_clamp
+    ; FLATSCRW32: renamable $vgpr0, renamable $vcc_lo = V_ADD_CO_U32_e64 12, $sgpr32, 1, implicit $exec
+    ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc_lo
+    renamable $vgpr0, renamable $vcc_lo = V_ADD_CO_U32_e64 12, %stack.0, 1, implicit $exec
+    SI_RETURN implicit $vgpr0, implicit $vcc_lo
+
+...
+
+---
+name: v_add_co_u32_e64__fi_literal_offset__sgpr
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 128, alignment: 16 }
+  - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+  scratchRSrcReg:  '$sgpr0_sgpr1_sgpr2_sgpr3'
+  frameOffsetReg:  '$sgpr33'
+  stackPtrOffsetReg: '$sgpr32'
+body:             |
+  bb.0:
+    liveins: $sgpr8
+    ; GFX940-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr
+    ; GFX940: liveins: $sgpr8
+    ; GFX940-NEXT: {{  $}}
+    ; GFX940-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+    ; GFX940-NEXT: $vgpr1 = V_MOV_B32_e32 killed $sgpr4, implicit $exec
+    ; GFX940-NEXT: renamable $vgpr0, renamable $vcc_lo = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 0, implicit $exec
+    ; GFX940-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc_lo
+    ;
+    ; GFX11-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr
+    ; GFX11: liveins: $sgpr8
+    ; GFX11-NEXT: {{  $}}
+    ; GFX11-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+    ; GFX11-NEXT: renamable $vgpr0, renamable $vcc_lo = V_ADD_CO_U32_e64 killed $sgpr4, $sgpr8, 0, implicit $exec
+    ; GFX11-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc_lo
+    ;
+    ; GFX12-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr
+    ; GFX12: liveins: $sgpr8
+    ; GFX12-NEXT: {{  $}}
+    ; GFX12-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+    ; GFX12-NEXT: renamable $vgpr0, renamable $vcc_lo = V_ADD_CO_U32_e64 killed $sgpr4, $sgpr8, 0, implicit $exec
+    ; GFX12-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc_lo
+    renamable $vgpr0, renamable $vcc_lo = V_ADD_CO_U32_e64 %stack.1, $sgpr8, 0, implicit $exec
+    SI_RETURN implicit $vgpr0, implicit $vcc_lo
+
+...
+
+---
+name: v_add_co_u32_e64__fi_literal_offset__sgpr_clamp
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 128, alignment: 16 }
+  - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+  scratchRSrcReg:  '$sgpr0_sgpr1_sgpr2_sgpr3'
+  frameOffsetReg:  '$sgpr33'
+  stackPtrOffsetReg: '$sgpr32'
+body:             |
+  bb.0:
+    liveins: $sgpr8
+    ; GFX940-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr_clamp
+    ; GFX940: liveins: $sgpr8
+    ; GFX940-NEXT: {{  $}}
+    ; GFX940-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+    ; GFX940-NEXT: $vgpr1 = V_MOV_B32_e32 killed $sgpr4, implicit $exec
+    ; GFX940-NEXT: renamable $vgpr0, renamable $vcc_lo = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 1, implicit $exec
+    ; GFX940-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc_lo
+    ;
+    ; GFX11-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr_clamp
+    ; GFX11: liveins: $sgpr8
+    ; GFX11-NEXT: {{  $}}
+    ; GFX11-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+    ; GFX11-NEXT: renamable $vgpr0, renamable $vcc_lo = V_ADD_CO_U32_e64 killed $sgpr4, $sgpr8, 1, implicit $exec
+    ; GFX11-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc_lo
+    ;
+    ; GFX12-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr_clamp
+    ; GFX12: liveins: $sgpr8
+    ; GFX12-NEXT: {{  $}}
+    ; GFX12-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+    ; GFX12-NEXT: renamable $vgpr0, renamable $vcc_lo = V_ADD_CO_U32_e64 killed $sgpr4, $sgpr8, 1, implicit $exec
+    ; GFX12-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc_lo
+    renamable $vgpr0, renamable $vcc_lo = V_ADD_CO_U32_e64 %stack.1, $sgpr8, 1, implicit $exec
+    SI_RETURN implicit $vgpr0, implicit $vcc_lo
+
+...
+
+---
+name: v_add_co_u32_e64__fi_literal_offset__vgpr
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 128, alignment: 16 }
+  - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+  scratchRSrcReg:  '$sgpr0_sgpr1_sgpr2_sgpr3'
+  frameOffsetReg:  '$sgpr33'
+  stackPtrOffsetReg: '$sgpr32'
+body:             |
+  bb.0:
+    liveins: $vgpr8
+
+    ; FLATSCRW32-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr
+    ; FLATSCRW32: liveins: $vgpr8
+    ; FLATSCRW32-NEXT: {{  $}}
+    ; FLATSCRW32-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+    ; FLATSCRW32-NEXT: renamable $vgpr0, dead renamable $vcc_lo = V_ADD_CO_U32_e64 killed $sgpr4, $vgpr8, 0, implicit $exec
+    ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+    renamable $vgpr0, renamable dead $vcc_lo = V_ADD_CO_U32_e64 %stack.1, $vgpr8, 0, implicit $exec
+    SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e64__fi_literal_offset__vgpr__clamp
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 128, alignment: 16 }
+  - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+  scratchRSrcReg:  '$sgpr0_sgpr1_sgpr2_sgpr3'
+  frameOffsetReg:  '$sgpr33'
+  stackPtrOffsetReg: '$sgpr32'
+body:             |
+  bb.0:
+    liveins: $vgpr8
+
+    ; FLATSCRW32-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr__clamp
+    ; FLATSCRW32: liveins: $vgpr8
+    ; FLATSCRW32-NEXT: {{  $}}
+    ; FLATSCRW32-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+    ; FLATSCRW32-NEXT: renamable $vgpr0, dead renamable $vcc_lo = V_ADD_CO_U32_e64 killed $sgpr4, $vgpr8, 1, implicit $exec
+    ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0
+    renamable $vgpr0, renamable dead $vcc_lo = V_ADD_CO_U32_e64 %stack.1, $vgpr8, 1, implicit $exec
+    SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e64__fi_literal_offset__vgpr__live_vcc
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 128, alignment: 16 }
+  - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+  scratchRSrcReg:  '$sgpr0_sgpr1_sgpr2_sgpr3'
+  frameOffsetReg:  '$sgpr33'
+  stackPtrOffsetReg: '$sgpr32'
+body:             |
+  bb.0:
+    liveins: $vgpr8
+
+    ; FLATSCRW32-LABEL: name: v_add_co_u32_e64__fi_literal_offset__vgpr__live_vcc
+    ; FLATSCRW32: liveins: $vgpr8
+    ; FLATSCRW32-NEXT: {{  $}}
+    ; FLATSCRW32-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+    ; FLATSCRW32-NEXT: renamable $vgpr0, renamable $vcc_lo = V_ADD_CO_U32_e64 killed $sgpr4, $vgpr8, 0, implicit $exec
+    ; FLATSCRW32-NEXT: SI_RETURN implicit $vgpr0, implicit $vcc_lo
+    renamable $vgpr0, renamable $vcc_lo = V_ADD_CO_U32_e64 %stack.1, $vgpr8, 0, implicit $exec
+    SI_RETURN implicit $vgpr0, implicit $vcc_lo
+
+...
+
+---
+name: v_add_co_u32_e64__inline_imm__fi_offset_literal__kernel__clamp
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 72, alignment: 16 }
+  - { id: 1, size: 40, alignment: 4 }
+machineFunctionInfo:
+  scratchRSrcReg:  '$sgpr0_sgpr1_sgpr2_sgpr3'
+  frameOffsetReg:  '$sgpr33'
+  stackPtrOffsetReg: '$sgpr32'
+  isEntryFunction: true
+body:             |
+  bb.0:
+    ; GFX940-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset_literal__kernel__clamp
+    ; GFX940: $sgpr4 = S_MOV_B32 72
+    ; GFX940-NEXT: renamable $vgpr0, dead $vcc_lo = V_ADD_CO_U32_e64 12, killed $sgpr4, 1, implicit $exec
+    ; GFX940-NEXT: SI_RETURN implicit $vgpr0
+    ;
+    ; GFX11-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset_literal__kernel__clamp
+    ; GFX11: renamable $vgpr0, dead $vcc_lo = V_ADD_CO_U32_e64 12, 72, 1, implicit $exec
+    ; GFX11-NEXT: SI_RETURN implicit $vgpr0
+    ;
+    ; GFX12-LABEL: name: v_add_co_u32_e64__inline_imm__fi_offset_literal__kernel__clamp
+    ; GFX12: renamable $vgpr0, dead $vcc_lo = V_ADD_CO_U32_e64 12, 72, 1, implicit $exec
+    ; GFX12-NEXT: SI_RETURN implicit $vgpr0
+    renamable $vgpr0, dead $vcc_lo = V_ADD_CO_U32_e64 12, %stack.1, 1, implicit $exec
+    SI_RETURN implicit $vgpr0
+
+...
+
+---
+name: v_add_co_u32_e64__fi_literal_offset__sgpr__scavenge_spill_required
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 128, alignment: 16 }
+  - { id: 1, size: 4, alignment: 4 }
+machineFunctionInfo:
+  scratchRSrcReg:  '$sgpr0_sgpr1_sgpr2_sgpr3'
+  frameOffsetReg:  '$sgpr33'
+  stackPtrOffsetReg: '$sgpr32'
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253, $vgpr254, $vgpr255, $sgpr8
+
+    ; GFX940-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr__scavenge_spill_required
+    ; GFX940: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+    ; GFX940-NEXT: {{  $}}
+    ; GFX940-NEXT: SCRATCH_STORE_DWORD_SADDR killed $vgpr1, $sgpr32, 132, 0, implicit $exec, implicit $flat_scr :: (store (s32) into %stack.2, addrspace 5)
+    ; GFX940-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+    ; GFX940-NEXT: $vgpr1 = V_MOV_B32_e32 killed $sgpr4, implicit $exec
+    ; GFX940-NEXT: renamable $vgpr0, renamable $vcc_lo = V_ADD_CO_U32_e64 killed $vgpr1, $sgpr8, 0, implicit $exec
+    ; GFX940-NEXT: $vgpr1 = SCRATCH_LOAD_DWORD_SADDR $sgpr32, 132, 0, implicit $exec, implicit $flat_scr :: (load (s32) from %stack.2, addrspace 5)
+    ; GFX940-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, implicit $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, implicit $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, implicit $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, implicit $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, implicit $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, implicit $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, implicit $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, implicit $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, implicit $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, implicit $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, implicit $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, implicit $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, implicit $vgpr248_vgpr249_vgpr250_vgpr251, implicit $vgpr252_vgpr253, implicit $vgpr254, implicit $vgpr255
+    ; GFX940-NEXT: SI_RETURN implicit $vgpr0
+    ;
+    ; GFX11-LABEL: name: v_add_co_u32_e64__fi_literal_offset__sgpr__scavenge_spill_required
+    ; GFX11: liveins: $sgpr8, $vgpr254, $vgpr255, $vgpr252_vgpr253, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239
+    ; GFX11-NEXT: {{  $}}
+    ; GFX11-NEXT: $sgpr4 = S_ADD_I32 $sgpr32, 128, implicit-def $scc
+    ; GFX11-NEXT: renamable $vgpr0, renamable $vcc_lo = V_ADD_CO_U32_e64 killed $sgpr4, $sgpr8, 0, implicit $exec
+    ; GFX11-NEXT: S_NOP 0, implicit $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, implicit $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vg...
[truncated]

arsenm

Remove GFX940 run lines and checks

arsenm · 2024-09-11T12:24:44Z

llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-co-u32-wave32.mir

@@ -0,0 +1,412 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# Test wave32
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx940 -mattr=+wavefrontsize32 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefixes=FLATSCRW32,GFX940 %s


This run line is nonsense, wave32 is not supported for gfx9

my bad will remove that. is the same case with predecessors gfx7,gfx8?

yes, wave32 was new in gfx10

llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-co-u32-wave32.mir

llvm-ci · 2024-09-13T08:30:01Z

LLVM Buildbot has detected a new failure on builder lldb-x86_64-debian running on lldb-x86_64-debian while building llvm at step 6 "test".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/162/builds/6198

Here is the relevant piece of the build log for the reference

Step 6 (test) failure: build (failure)
...
XFAIL: lldb-api :: lang/c/modules/TestCModules.py (469 of 2680)
PASS: lldb-api :: functionalities/breakpoint/breakpoint_reset_upon_run/TestBreakpointResetUponRun.py (470 of 2680)
PASS: lldb-api :: lang/cpp/exceptions/TestCPPExceptionBreakpoints.py (471 of 2680)
PASS: lldb-api :: functionalities/data-formatter/summary-string-onfail/Test-rdar-9974002.py (472 of 2680)
PASS: lldb-api :: lang/cpp/incompatible-class-templates/TestCppIncompatibleClassTemplates.py (473 of 2680)
PASS: lldb-api :: functionalities/thread/concurrent_events/TestConcurrentCrashWithSignal.py (474 of 2680)
PASS: lldb-api :: functionalities/thread/concurrent_events/TestConcurrentSignalBreak.py (475 of 2680)
PASS: lldb-api :: commands/settings/quoting/TestQuoting.py (476 of 2680)
PASS: lldb-api :: functionalities/thread/concurrent_events/TestConcurrentTwoBreakpointsOneSignal.py (477 of 2680)
PASS: lldb-api :: lang/c/struct_types/TestStructTypes.py (478 of 2680)
FAIL: lldb-api :: tools/lldb-dap/attach/TestDAP_attach.py (479 of 2680)
******************** TEST 'lldb-api :: tools/lldb-dap/attach/TestDAP_attach.py' FAILED ********************
Script:
--
/usr/bin/python3 /home/worker/2.0.1/lldb-x86_64-debian/llvm-project/lldb/test/API/dotest.py -u CXXFLAGS -u CFLAGS --env ARCHIVER=/usr/bin/ar --env OBJCOPY=/usr/bin/objcopy --env LLVM_LIBS_DIR=/home/worker/2.0.1/lldb-x86_64-debian/build/./lib --env LLVM_INCLUDE_DIR=/home/worker/2.0.1/lldb-x86_64-debian/build/include --env LLVM_TOOLS_DIR=/home/worker/2.0.1/lldb-x86_64-debian/build/./bin --arch x86_64 --build-dir /home/worker/2.0.1/lldb-x86_64-debian/build/lldb-test-build.noindex --lldb-module-cache-dir /home/worker/2.0.1/lldb-x86_64-debian/build/lldb-test-build.noindex/module-cache-lldb/lldb-api --clang-module-cache-dir /home/worker/2.0.1/lldb-x86_64-debian/build/lldb-test-build.noindex/module-cache-clang/lldb-api --executable /home/worker/2.0.1/lldb-x86_64-debian/build/./bin/lldb --compiler /home/worker/2.0.1/lldb-x86_64-debian/build/./bin/clang --dsymutil /home/worker/2.0.1/lldb-x86_64-debian/build/./bin/dsymutil --llvm-tools-dir /home/worker/2.0.1/lldb-x86_64-debian/build/./bin --lldb-obj-root /home/worker/2.0.1/lldb-x86_64-debian/build/tools/lldb --lldb-libs-dir /home/worker/2.0.1/lldb-x86_64-debian/build/./lib -t /home/worker/2.0.1/lldb-x86_64-debian/llvm-project/lldb/test/API/tools/lldb-dap/attach -p TestDAP_attach.py
--
Exit Code: 1

Command Output (stdout):
--
lldb version 20.0.0git (https://github.com/llvm/llvm-project.git revision 991c842b38ec829d7a4bda432555673a310b777e)
  clang revision 991c842b38ec829d7a4bda432555673a310b777e
  llvm revision 991c842b38ec829d7a4bda432555673a310b777e
pid = 2100709
Skipping the following test categories: ['libc++', 'dsym', 'gmodules', 'debugserver', 'objc']
========= DEBUG ADAPTER PROTOCOL LOGS =========
1726216123.125415087 --> 
Content-Length: 344

{
  "arguments": {
    "adapterID": "lldb-native",
    "clientID": "vscode",
    "columnsStartAt1": true,
    "linesStartAt1": true,
    "locale": "en-us",
    "pathFormat": "path",
    "sourceInitFile": false,
    "supportsRunInTerminalRequest": true,
    "supportsStartDebuggingRequest": true,
    "supportsVariablePaging": true,
    "supportsVariableType": true
  },
  "command": "initialize",
  "seq": 1,
  "type": "request"
}
1726216123.128045321 <-- 
Content-Length: 1556

PankajDwivedi-25 added 2 commits September 9, 2024 12:59

[WIP][AMDGPU] eliminate frame index v_add wave32 test

7bf2e51

[AMDGPU] updated test checks

f273492

PankajDwivedi-25 added the backend:AMDGPU label Sep 9, 2024

PankajDwivedi-25 requested a review from arsenm September 9, 2024 09:52

PankajDwivedi-25 changed the title ~~[AMDGPU] eliminate frame index v add wave32 test~~ [AMDGPU] eliminate frame index v_add wave32 test Sep 9, 2024

arsenm requested changes Sep 11, 2024

View reviewed changes

arsenm reviewed Sep 11, 2024

View reviewed changes

llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-co-u32-wave32.mir Outdated Show resolved Hide resolved

[AMDGPU] updated run line and checks

5cc0e4e

arsenm approved these changes Sep 13, 2024

View reviewed changes

PankajDwivedi-25 merged commit 991c842 into llvm:main Sep 13, 2024
8 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[AMDGPU] eliminate frame index v_add wave32 test #107832

[AMDGPU] eliminate frame index v_add wave32 test #107832

Uh oh!

PankajDwivedi-25 commented Sep 9, 2024

Uh oh!

llvmbot commented Sep 9, 2024

Uh oh!

arsenm left a comment

Uh oh!

arsenm Sep 11, 2024

Uh oh!

PankajDwivedi-25 Sep 11, 2024 •

edited

Loading

Uh oh!

arsenm Sep 12, 2024

Uh oh!

Uh oh!

Uh oh!

llvm-ci commented Sep 13, 2024

Uh oh!

Uh oh!

[AMDGPU] eliminate frame index v_add wave32 test #107832

[AMDGPU] eliminate frame index v_add wave32 test #107832

Uh oh!

Conversation

PankajDwivedi-25 commented Sep 9, 2024

Uh oh!

llvmbot commented Sep 9, 2024

Uh oh!

arsenm left a comment

Choose a reason for hiding this comment

Uh oh!

arsenm Sep 11, 2024

Choose a reason for hiding this comment

Uh oh!

PankajDwivedi-25 Sep 11, 2024 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

arsenm Sep 12, 2024

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

llvm-ci commented Sep 13, 2024

Uh oh!

Uh oh!

PankajDwivedi-25 Sep 11, 2024 •

edited

Loading